CN110070391A - Data processing method, device, computer-readable medium and electronic equipment - Google Patents
Data processing method, device, computer-readable medium and electronic equipment Download PDFInfo
- Publication number
- CN110070391A CN110070391A CN201910307427.9A CN201910307427A CN110070391A CN 110070391 A CN110070391 A CN 110070391A CN 201910307427 A CN201910307427 A CN 201910307427A CN 110070391 A CN110070391 A CN 110070391A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- score value
- interest score
- product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This disclosure relates to technical field of data processing, in particular to a kind of data processing method, device, computer readable storage medium and electronic equipment.Wherein, the above method includes: the forecast demand for obtaining customer data base and the first data-interface, wherein the customer data base is determined according to the data information of data information and/or first data-interface from the second data-interface；According to the forecast demand in the customer data base matched data, to obtain the behavioral data of first object user；Based on interest score value prediction model, interest score value of the first object user about target product is determined according to the behavioral data；The processing strategie to the first object user is determined according to the interest score value.The technical program is based on big data and carries out predicting to be conducive to improve forecasting accuracy, and prediction result fitting is practical, is conducive to be promoted market response rate and marketing conversion ratio.
Description
Technical field
This disclosure relates to which technical field of data processing, fills in particular to a kind of data processing method, data processing
It sets, and realizes the computer readable storage medium and electronic equipment of the data processing method.
Background technique
The method of present marketing product usually selects user at random, then by being made a phone call to the user selected and
Short message is sent to market.For example, credit agency selects user at random, short message is made a phone call or sent to user and is marketed to it
Credit product.In another example insurance company selects user at random, short message is made a phone call or sent to user to its insurance products of marketing
Deng.
However, existing marketing mode is at high cost, the waste of manpower and material resources is not only caused, but also by the sound of marketing personnel
Should rate it is low.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The embodiment of the present disclosure is designed to provide a kind of data processing method, data processing equipment, and described in realizing
The computer readable storage medium and electronic equipment of data processing method, so at least to a certain extent save marketing at
This, and improve marketing response rate.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the first aspect of the embodiments of the present disclosure, a kind of data processing method is provided, comprising:
Obtain the forecast demand of customer data base and the first data-interface, wherein the customer data base is according to coming from the
The data information of the data information of two data-interfaces and/or first data-interface determines；
According to the forecast demand in the customer data base matched data, to obtain the behavior number of first object user
According to；
Based on interest score value prediction model, determine the first object user about target product according to the behavioral data
Interest score value；
The processing strategie to the first object user is determined according to the interest score value.
According to the forecast demand in the customer data base matched data, to obtain the behavior number of first object user
According to, comprising:
Based on the identity of the first object user, according to the feature of target product in the forecast demand, in institute
Matched data in customer data base is stated, the behavioral data of the first object user is obtained.
In some embodiments of the present disclosure, it is based on aforementioned schemes, the data processing method further include:
It obtains sample data and training machine learning model obtains the interest score value prediction model.
In some embodiments of the present disclosure, aforementioned schemes are based on, sample data is obtained and training machine learning model obtains
To the interest score value prediction model, comprising:
The corresponding candidate samples data of multidimensional candidate variables are obtained from the customer data base；
For at least one product, the candidate samples data of response data will be generated within a preset time as positive sample number
According to, and, using the candidate samples data of non-output response within a preset time as negative sample data；
For at least one product, screens the multidimensional candidate variables and obtain the corresponding target sample data of target variable；
Based on target sample data training Logic Regression Models, obtain pre- about the interest score value of at least one product
Survey model.
In some embodiments of the present disclosure, aforementioned schemes are based on, the multidimensional candidate variables is screened and obtains target variable
Corresponding target sample data, comprising:
Predictive ability value according to the candidate samples data acquisition per one-dimensional candidate variables；
The corresponding candidate variables of predictive ability value of preset condition will be met as the target variable, to obtain the mesh
Mark the corresponding target sample data of variable.
In some embodiments of the present disclosure, aforementioned schemes are based on, the multidimensional candidate variables include: user about at least
Preference data about different product of a kind of behavioral data of product, user internet behavioral data, user, user social contact relationship
One or more of data.
In some embodiments of the present disclosure, aforementioned schemes are based on, interest score value prediction model are based on, according to the behavior
Data determine interest score value of the first object user about target product, comprising:
According to the behavioral data, the corresponding target variable of N kind product is determined, wherein N is the positive integer more than or equal to 1；
The target variable is input to the interest score value prediction model, obtains output result；
According to the output as a result, determining interest score value of the first object user about the N kind product.
In some embodiments of the present disclosure, aforementioned schemes are based on, are determined according to the interest score value to first mesh
Mark the marketing strategy of user, comprising:
For i-th kind of product in the N kind product:
According to the interest score value about i-th kind of credit product, by the first object user stratification；
For the first object user of different layers, the different disposal strategy about i-th kind of product is determined, wherein i is big
It is less than or equal to N in being equal to 1.
In some embodiments of the present disclosure, aforementioned schemes are based on, the target variable includes: user about at least one
Preference data, user social contact relation data of the behavioral data, user internet behavioral data, user of product about different product
One or more of.
In some embodiments of the present disclosure, aforementioned schemes are based on, are determined according to the interest score value to described first
After the processing strategie of target user, the method also includes:
The customer data base is updated according to the output result of the interest score value prediction model.
In some embodiments of the present disclosure, it is based on aforementioned schemes, the data processing method further include:
User's portrait of the first object user is determined according to the output result of the interest score value prediction model, it is described
User's portrait includes multiple user tags；
The forecast demand from second interface is matched according to the user tag, to determine from the first object user
Second target user is recommended the second interface by the second target user.
According to the second aspect of an embodiment of the present disclosure, a kind of data processing equipment is provided, comprising:
Database obtains module, for obtaining the forecast demand of customer data base and the first data-interface, wherein the use
User data library is determined according to the data information of data information and/or first data-interface from the second data-interface；
Behavioral data obtain module, for according to the forecast demand in the customer data base matched data, to obtain
Take the behavioral data of first object user；
Interest score value determining module determines described the according to the behavioral data for being based on interest score value prediction model
Interest score value of one target user about target product；
Tactful determining module, for determining the processing strategie to the first object user according to the interest score value.
According to the third aspect of an embodiment of the present disclosure, a kind of computer readable storage medium is provided, meter is stored thereon with
Calculation machine program realizes the data processing method as described in first aspect in above-described embodiment when described program is executed by processor.
According to a fourth aspect of embodiments of the present disclosure, a kind of electronic equipment is provided, comprising: one or more processors；
Storage device, for storing one or more programs, when one or more of programs are held by one or more of processors
When row, so that one or more of processors realize the data processing method as described in first aspect in above-described embodiment.
The technical solution that the embodiment of the present disclosure provides can include the following benefits:
On the one hand, in the technical solution provided by some embodiments of the present disclosure, by by all kinds of means (and be not limited to work as
Preceding client) data information is obtained to determine customer data base, and according to the existing customer (i.e. above-mentioned the from the first data-interface
One client) forecast demand in this customer data base matched data, to obtain the behavioral data of its target user, and then to work as
Preceding client provides more comprehensively target user's information.Meanwhile comprehensive behavioral data is conducive to the user of abundant target user
Portrait, and then be conducive to improve the forecasting accuracy of interest score value, to improve marketing specific aim and marketing efficiency.
On the other hand, in the technical solution provided by some embodiments of the present disclosure, pass through the machine learning after training
Model prediction target user carries out prediction based on big data and is conducive to improve forecasting accuracy to the interest score value of marketing product,
Prediction result fitting is practical, is conducive to the marketing response rate for promoting Related product and marketing conversion ratio.
In another aspect, being the first of different interest score values in the technical solution provided by some embodiments of the present disclosure
Target user determines different processing strategies (such as to the marketing strategy of target product), the high intention of Effective selection and can meet money
The target user of matter is conducive to further promote marketing response rate and marketing conversion ratio.Meanwhile target is used according to interest peak value
Family layered shaping can be avoided and bother no intention user, to promote user experience.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.In the accompanying drawings:
Fig. 1 shows the flow diagram of the data processing method according to the embodiment of the present disclosure；
Fig. 2 shows the flow diagrams according to the determination method of the interest score value prediction model of the embodiment of the present disclosure；
Fig. 3 shows the flow diagram of the determination method of the target sample data according to the embodiment of the present disclosure；
Fig. 4 shows the determination method of the interest score value of the first object user according to the embodiment of the present disclosure；
Fig. 5 shows the flow diagram of the determination method according to the marketing strategy of the embodiment of the present disclosure；
Fig. 6 shows the structural schematic diagram of data processing equipment according to an embodiment of the present disclosure；
Fig. 7 schematically shows a kind of computer readable storage medium for realizing above-mentioned data processing method；And
Fig. 8 schematically shows a kind of electronic equipment example block diagram for realizing above-mentioned data processing method.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to embodiment of the disclosure.However,
It will be appreciated by persons skilled in the art that can with technical solution of the disclosure without one or more in specific detail,
Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known side
Method, device, realization or operation are to avoid fuzzy all aspects of this disclosure.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuit
These functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,
It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can close
And or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
It is existing in the related technology, by select at random user be unfolded marketing, do not consider whether it needs credit product,
It is sent short messages or is made a phone call to market.The marketing mode marketing efficiency of this specific aim difference is low, and will bother without debt-credit wish
User, or even many customer complaints can be connected to and user is caused to dislike.Meanwhile cost of marketing is high, many people, which do not borrow or lend money, to be needed
It asks, but extensively sends short messages and make a phone call, inherently need certain cost of marketing, not only have little effect, also waste of manpower resource.
Fig. 1 shows the flow diagram of the data processing method according to the embodiment of the present disclosure, can be at least in certain journey
Cost of marketing is saved on degree, and improves marketing response rate.
Wherein, the executing subject of data processing method provided in this embodiment can be setting with calculation processing function
It is standby, such as the server of credit product third-party platform, wherein credit product third-party platform can mention for different finance companies
For marketing strategy.
The data processing method provided with reference to Fig. 1, the embodiment, comprising:
Step S110 obtains the forecast demand of customer data base and the first data-interface, wherein the customer data base root
It is determined according to the data information of data information and/or first data-interface from the second data-interface；
Step S120, according to the forecast demand in the customer data base matched data, with obtain first object use
The behavioral data at family；
Step S130 is based on interest score value prediction model, determines that the first object user is closed according to the behavioral data
In the interest score value of target product；And
Step S140 determines the processing strategie to the first object user according to the interest score value.
In technical solution provided by embodiment shown in Fig. 1, on the one hand, by by all kinds of means (and be not limited to current visitor
Family) data information is obtained to determine customer data base, and according to existing customer (i.e. above-mentioned first visitor from the first data-interface
Family) forecast demand in this customer data base matched data, to obtain the behavioral data of its target user, and then be current visitor
Family provides more comprehensively target user's information, meanwhile, comprehensive behavioral data is conducive to user's portrait of abundant target user,
And then be conducive to improve the forecasting accuracy of interest score value, to improve marketing specific aim and marketing efficiency.
On the other hand, predict target user to the interest score value of marketing product, base by the machine learning model after training
It carries out prediction in big data to be conducive to improve forecasting accuracy, prediction result fitting is practical, is conducive to the battalion for promoting Related product
Sell response rate and marketing conversion ratio.
In another aspect, the first object user for different interest score values determines different marketing strategies, it being capable of Effective selection
High intention and the target user for meeting qualification are conducive to further promote marketing response rate and marketing conversion ratio.Meanwhile according to emerging
Interesting peak value can be avoided and bother no intention user, to promote user experience to target user's layered shaping.
The specific embodiment of each step in embodiment illustrated in fig. 1 is described in detail below.
In the exemplary embodiment, credit product third-party platform receives the forecast demand of different finance companies.This reality
It applies in example, different data-interfaces is set for different finance companies, then the forecast demand from the first data-interface is from the
The forecast demand of one finance company (the first client).
Wherein, above-mentioned first client can be used to indicate that existing customer, and above-mentioned second client can be used to indicate that in addition to
Other one or more clients except existing customer.In the present embodiment, above-mentioned user is determined according to the user data of multiple clients
Database.In turn, the data that the determining forecast demand with existing customer matches in customer data base.Worked as with obtaining to correspond to
The behavioral data of the first object user of preceding client.For example, A credit agency (existing customer) is using s user as its target user,
But there is no have a information to come and go with A credit agency by s user.By expanding the data source in database in the present embodiment,
It avoids existing customer and understands its target customer deficient problem.
In the exemplary embodiment, in above-mentioned customer data base, user characteristics are distinguished by User Identity.
Further, according to the specific implementation of forecast demand matched data in above-mentioned customer data base of the first client in step S110
Mode may is that the identity based on first object user, according to the feature for product of marketing in the forecast demand, in institute
Matched data in customer data base is stated, the behavioral data of the first object user is obtained.Illustratively, the first client intends battalion
The feature for selling product includes: small short-term loan, installment reimbursement etc., and the identity of target user is ID1.Then by number of users
According to the behavioral data in library about the data of ID1 and corresponding time point as above-mentioned first object client.Pass through identity mark
Knowledge is marked and distinguishes to the data in customer data base, is conducive to obtain complete in the entire credit life cycle of target user
Portion's data, and then mould more comprehensive user's portrait.So that the interest score value prediction of Behavior-based control data it is more accurate,
With more persuasion property.
In the exemplary embodiment, above-mentioned customer data base is real-time update, such as the use that existing customer is provided
User data real-time update is into customer data base, so that the data comprehensive and abundant in customer data base, to merge multidimensional data
More fully customer portrait label system is established, natural quality, financial asset, the letter of building user are identified based on different identity
The feature tags such as attribute, life style, interest preference are borrowed, provide more supports for marketing activity.
In the exemplary embodiment, the behavioral data of above-mentioned first object user, can be and obtain from customer data base
The historical behavior data taken.It is also possible to the data generated in current marketing process.For example, user is currently complete in credit agency
It at registration, then obtains whether user will appear data such as application debt-credit etc. within following a period of time, can also be used as user
Behavioral data.
In the exemplary embodiment, interest score value prediction model is by obtaining sample data and training in step S130
What machine learning model obtained.In the exemplary embodiment, above-mentioned machine learning model can be Logic Regression Models, decision
Tree-model, artificial neural network ANN etc..Illustratively, by taking Logic Regression Models as an example, Fig. 2 shows according to disclosure reality
Apply the flow diagram of the determination method of the interest score value prediction model of example.With reference to Fig. 2, the method which provides includes step
Rapid S210- step S240.
In step S210, the corresponding candidate samples data of multidimensional candidate variables are obtained from the customer data base.
In the exemplary embodiment, sample needed for obtaining machine learning in above-mentioned customer data base.In addition, multidimensional is waited
Selecting vector is the variable that the output (interest score value) with machine learning model may have an impact, and is to machine learning model
Export influential variable.If the output of machine learning model is the interest score value to credit product, then above-mentioned multidimensional is candidate
Variable may include: user's lend-borrow action data, user internet behavioral data, Financial Attribute data, personal debt-credit preference number
According to, social networks data, age of user section, user's gender, user job type and whether had and bought credit product
Deng.
Candidate samples data corresponding for above-mentioned multidimensional candidate variables, need to further be marked by step S220
Processing.It is specific:
In step S220, at least one product, the candidate samples number of response data will be generated within a preset time
According to as positive sample data, and, using the candidate samples data of non-output response within a preset time as negative sample data.
In the exemplary embodiment, it for above-mentioned candidate samples data, (such as one month) will produce within a preset time
The label of raw corresponding data is.Conversely, the candidate samples data of non-output response are as negative sample within a preset time
Data.For example, in the marketing process of credit agency, the candidate variables for being 30-35 years old for age bracket go not apply for registration
The user of debt-credit, can choose registion time is observation time starting point, observes whether it has application to borrow or lend money in one month later.
It by this sample is to determine age of user section (candidate variables) corresponding positive sample if application debt-credit occurs；If application does not occur to borrow
Borrowing then is to determine age of user section (candidate variables) corresponding negative sample by this sample.And processing method is marked according to this, by it
Candidate samples data corresponding with candidate variables are handled.
In the exemplary embodiment, the interest score value prediction model that the technical program provides is produced to a kind of credit is not limited to
The interest score value of product is predicted.Illustratively, the feature of credit product L includes: small short-term loan, installment reimbursement system；Letter
The feature for borrowing product M includes: wholesale long-term loan, installment reimbursement system；The feature of credit product N includes: wholesale long-term loan, non-
Installment reimbursement system.That is, being determined the response data of the credit product of different characteristic type to different characteristic according to user
Credit product interest score value handle model.To meet client (credit agency) to the forecast demand of different credit products,
Be conducive to improve the prediction experience of client.
In the exemplary embodiment, to each credit product, it is provided with different business scenarios, comprising: potential new
User's scene, registration are not applied borrowing or lending money scene, apply for that debt-credit does not draw business scenario, closes and do not borrow one of scene or several again
Kind.For the different scenes of each credit product, by the corresponding candidate samples data markers of multidimensional candidate feature be positive sample,
Negative sample.As it can be seen that after determining candidate samples data, it is derivative by data processing conversion and/or feature, realize that more credits produce
The setting of product, multi-service scene, and then the interest score value of target user can be predicted from various dimensions.The scene of model is abundant, industry
Business understands that the new marketing mode of business combination scene brings new internet marketing mode to credit industry deeply.For example,
User q can be predicted to the interest score value of different credit products, to infer the user tag for belonging to user q, and then abundant use
The user of family q draws a portrait, and is conducive to be that user q matches high wish credit product according to user tag.For another example different by statistics
User behavior data in business scenario is conducive to client (credit agency) discovery potential user, to be conducive to potential customers
Development is storage client etc..
In step S230, at least one product, screening the multidimensional candidate variables, to obtain target variable corresponding
Target sample data.
In the exemplary embodiment, Fig. 3 shows the determination method of the target sample data according to the embodiment of the present disclosure
Flow diagram, be particularly used in a kind of specific embodiment of interpretation procedure S230.With reference to Fig. 3, this method comprises:
In step s310, the predictive ability value according to the candidate samples data acquisition per one-dimensional candidate variables.
For the candidate samples data after label processing, Feature Selection processing is carried out.Especially by information value
The predictive ability that (Information Value, referred to as: IV) measures candidate variables, then according to the height of IV to candidate feature
It is screened.By the Screening Treatment to variable, the model variable of high-quality stable is picked out, makes interest score value model in the later period
In, there is stronger stability and interpretation.
In the exemplary embodiment, (1) encodes a candidate variables WOE, specifically: by the corresponding candidate of candidate variables
Sample data is grouped processing (sliding-model control or branch mailbox is also made to handle).Then, it for i-th group, is calculated by formula one
WOEi；
In formula one, pyiBe this candidate variables i-th group of candidate samples in be marked as positive sample and account for institute in all samples
There are the ratio of customer in response, pniBe this candidate variables i-th group of candidate samples in be marked as negative sample and account for institute in all samples
There are the ratio of customer in response, #yiBe this candidate variables i-th group of candidate samples in be marked as the quantity of positive sample, #niIt is this
The quantity of negative sample, #y are marked as in i-th group of candidate samples of candidate variablesTIt is in the corresponding candidate samples of this candidate variables
It is marked as the total quantity of positive sample, #nTThe total quantity of negative sample is marked as in the corresponding candidate samples of this candidate variables.
(2) according to WOEiCoding calculates the IV of candidate variablesi, specifically: for i-th group, IV being calculated by formula twoi；
IVi=(pyi-pni)*WOEiFormula two (3)
By all groups of IV of this candidate variablesiSummation obtains the corresponding IV of this candidate variables.Further, all candidate changes are calculated
The IV of amount.
In step s 320, the corresponding candidate variables of predictive ability value for meeting preset condition are become as the target
Amount, to obtain the corresponding target sample data of the target variable.
The candidate variables that IV value is greater than preset threshold are made as target variable, and by the corresponding sample data of target variable
For target sample data.Alternatively, the IV of all candidate variables can also be arranged from high to low, by the corresponding candidate of preceding X IV
Variable is as target variable.Wherein, X is positive integer.
With continued reference to Fig. 2, in step S240, based on target sample data training Logic Regression Models, closed
In the interest score value prediction model of at least one product.
In the exemplary embodiment, target sample can be divided into experimental group and control group, further with accuracy rate,
Recall rate, AUC measure the model after training as the test index of model training.And it can reach default when above-mentioned test index
Stop the training to model when threshold value, obtains interest score value prediction model.
In the technical solution that Fig. 2 and embodiment illustrated in fig. 3 are provided, setting includes multi-service scene, a variety of credit products
Target sample data, interest score value prediction model of the training about credit product.Machine learning based on the training of this big data
Model can effectively know prediction user to the interestingness score of different credit products, to obtain Gao Yi for client (credit agency)
To low-risk visitor group.Since credit agency does not have any information to silencing client, so false customer revenue can not be identified effectively.
Prediction model based on interest score value can identify potential user, activation silent user, and can effectively tell those is false stream
Client is lost, and assesses it and activates response probability, effectively excavates silencing customer value, constantly improve purchase rate again.To avoid credit
Mechanism miss potential user or while silent user, further increases marketing response rate.
Fig. 4 shows the determination method of the interest score value of the first object user according to the embodiment of the present disclosure, specific to provide
A kind of specific embodiment of step S130.With reference to Fig. 4, the method comprising the steps of S410- step S430.
In step S410, according to the behavioral data, determine the corresponding target variable of N kind product, wherein N be greater than
Positive integer equal to 1.
In the exemplary embodiment, the feature of the marketing product E provided according to the first client, first object user's
The target variable about credit product E is determined in behavioral data, may include: behavior number of the user about at least one product
According to, user internet behavioral data, user about one of the preference data of different product, user social contact relation data or several
Kind.To according to the determining available user of object vector of the method to the interest score value of credit product E.
In the exemplary embodiment, the identity for the target user that can also be provided according to the first client, determines the
Behavioral data of one target user about a variety of credit products, to be determined in the behavioral data about a variety of credit products each
The target variable of kind credit product.For example, the corresponding target variable of credit product W is variable w1, variable w2, credit product W ' is right
The target variable answered is variable w1 ', variable w2 '.To which user couple can be respectively obtained according to the object vector that the method determines
The interest score value of credit product W and interest score value to credit product W '.And then for client (credit agency) provide about with
The information of family intention is conducive to the further marketing of client's expansion.
In the step s 420, the target variable is input to the interest score value prediction model, obtains output result.
In the exemplary embodiment, the output result of interest score value prediction model can be set are as follows: the score of 0-100,
Interest score value is higher, and it is strong that reflection user borrows or lends money wish.Such as: the debt-credit of ten equal part of score, 90-100 score section is responded into crowd
Certainly the debt-credit for being higher than 80-90 score section responds crowd, and so on, decline trend should be presented in each score section.
It in the exemplary embodiment, can love-Si meter love inspection (Kolmogorov-Smirnov by Ke Ermo
Test, referred to as: KS- is examined) the risk separating capacity of above-mentioned interest score value model is assessed, what KS index was measured is quality
Sample adds up the difference between branch.The accumulative difference of fine or not sample is bigger, and KS index is bigger, then the risk separating capacity of model
It is stronger.Steps are as follows for the calculating of KS:
1. calculating the fine or not account number in each scoring section；
2. calculate each scoring section has added up account number Zhan always good account percentage (good%) and accumulative bad credit family
The number total bad credit amount ratio (bad%) of Zhan；
(add up 3. calculating each scoring section and adding up bad credit family accounting with account accounting absolute value of the difference has been added up
Good%- adds up bad%), then these absolute values are maximized with the KS value up to this scorecard.
In the exemplary embodiment, it with the gradually accumulation of marketing feedback data in customer data base, is added more special
The variable training above-mentioned interest score value prediction model of iteration is levied, to improve predictablity rate.
In step S430, according to the output as a result, determining the first object user about the emerging of the N kind product
Interesting score value.
In the exemplary embodiment, Fig. 5 shows the stream of the determination method according to the marketing strategy of the embodiment of the present disclosure
Journey schematic diagram specifically provides a kind of specific embodiment of step S140.With reference to Fig. 5, the method comprising the steps of S510 and step
Rapid S520.
For i-th kind of product in the N kind credit product:
In step S510, according to the interest score value about i-th kind of product, by the first object user stratification.
And in step S520.For the first object user of different layers, the different marketing plans about i-th kind of product are determined
Slightly, wherein i is more than or equal to 1 and is less than or equal to N.
In the exemplary embodiment, about a certain credit product, to first in the higher layering of interest score value
The marketing activity about this credit product is unfolded in target user.And to the first object in the lower layering of interest score value
User wouldn't be unfolded about this credit product marketing activity.To the first object user in the lower layering of interest score value,
Its interest score value to other credit products can be counted, further to market other products to these users.To for height
Intention user's active marketing reaches low intention user without touching, while promoting conversion success rate reduces cost of marketing, keeps away
Exempt to bother no intention user.The response rate for being conducive to greatly improve marketing debt-credit crowd, has not only saved cost, has also improved
The registration rate of credit agency, into part rate and rate of making loans.
In the exemplary embodiment, the first object is determined according to the output result of the interest score value prediction model
The user of user draws a portrait, and user's portrait includes multiple user tags.Such as: user's a preference small amount is borrowed or lent money by stages, user b
Preference wholesale long term borrowings etc..Further, the forecast demand of the second client (other credit agencies) is matched according to user tag,
To determine the second target user from the first object user, and second target user is recommended into second visitor
Family.It is drawn a portrait by user, client can be allowed to know more about its user sources, interest.User is recalled by screening target, optimizes credit
The marketing activity of mechanism.By the further analysis to output result, the plans such as amount adjustment, marketing methods, marketing time are provided
Slightly suggest, to meet the marketing demand of different credit agencies.
Technical solution provided in this embodiment is the new objective acquisition stage of credit agency, deposit that objective operation stage provides it is one whole
User's Loan Demand Analysis Service is covered, with the more efficient marketing of power-assisted credit agency and finer operation.
It should be noted that the various embodiments described above are to be predicted with the interest score value of credit product, and be based on interest
What score value was illustrated for marketing to credit product.In addition, the technical program can also be the insurance to insurance company
The interest score value of product is predicted, and is marketed etc. based on interest score value to insurance products.
The Installation practice of the disclosure introduced below can be used for executing the above-mentioned data processing method of the disclosure.
Fig. 6 diagrammatically illustrates the structural schematic diagram of data processing equipment according to an embodiment of the present disclosure.With reference to Fig. 6,
Above-mentioned data processing equipment 600, comprising: database obtains module 601, behavioral data obtains module 602, interest score value determines mould
Block 603, and tactful determining module 604.
Wherein, above-mentioned database obtains module 601, and the prediction for obtaining customer data base and the first data-interface needs
It asks, wherein the customer data base is according to the number of data information and/or first data-interface from the second data-interface
It is believed that breath determines；
Above-mentioned behavioral data obtains module 602, for according to the forecast demand in the customer data base coupling number
According to obtain the behavioral data of first object user；
Above-mentioned interest score value determining module 603 is determined for being based on interest score value prediction model according to the behavioral data
Interest score value of the first object user about target product；
Above-mentioned strategy determining module 604, for determining the processing to the first object user according to the interest score value
Strategy.
In the exemplary embodiment, aforementioned schemes are based on, above-mentioned behavioral data obtains module 602, is specifically used for: being based on
The identity of the first object user, according to the feature of target product in the forecast demand, in the customer data base
Middle matched data obtains the behavioral data of the first object user.
In the exemplary embodiment, aforementioned schemes, above-mentioned data processing equipment 600 further include: machine learning mould are based on
Type training module.
Wherein, above-mentioned machine learning model training module is used for: obtaining sample data and training machine learning model obtains
The interest score value prediction model.
In the exemplary embodiment, aforementioned schemes, above-mentioned machine learning model training module are based on, comprising: obtain single
Member, mark unit, screening unit and training unit.
Wherein, above-mentioned acquiring unit is used for: obtaining the corresponding candidate samples of multidimensional candidate variables from the customer data base
Data；
Above-mentioned mark unit is used for: at least one product, will generate the candidate sample of response data within a preset time
Notebook data as positive sample data, and, using the candidate samples data of the response of non-output within a preset time as negative sample number
According to；
Above-mentioned screening unit is used for: at least one product, being screened the multidimensional candidate variables and is obtained target variable pair
The target sample data answered；
Above-mentioned training unit is used for: based on target sample data training Logic Regression Models, being obtained about at least one
The interest score value prediction model of kind product.
In the exemplary embodiment, aforementioned schemes are based on, above-mentioned screening unit is specifically used for: according to the candidate sample
Notebook data obtains the predictive ability value per one-dimensional candidate variables；And the corresponding time of predictive ability value that preset condition will be met
Select variable as the target variable, to obtain the corresponding target sample data of the target variable.
In the exemplary embodiment, aforementioned schemes are based on, the multidimensional candidate variables include: user about at least one
Preference data of the lend-borrow action data, user internet behavioral data, user of product about different product, user social contact relationship
One or more of data.
In the exemplary embodiment, aforementioned schemes are based on, above-mentioned interest score value determining module 603 is specifically used for: according to
The behavioral data determines the corresponding target variable of N kind product, wherein N is the positive integer more than or equal to 1；The target is become
Amount is input to the interest score value prediction model, obtains output result；And according to the output as a result, determining described first
Interest score value of the target user about the N kind product.
In the exemplary embodiment, aforementioned schemes are based on, above-mentioned strategy determining module 604 is specifically used for: for described
I-th kind of credit product in N kind credit product: according to the interest score value about i-th kind of credit product, by first mesh
Mark user stratification；And the first object user for different layers, determine the difference about i-th kind of target credit product
Marketing strategy, wherein i is more than or equal to 1 and is less than or equal to N.
In the exemplary embodiment, aforementioned schemes are based on, the target variable includes: user about at least one product
Behavioral data, user internet behavioral data, user is about in the preference data of different product, user social contact relation data
It is one or more of.
In the exemplary embodiment, aforementioned schemes, above-mentioned data processing equipment 600 further include: database update are based on
Module.
Wherein, the battalion to the first object user is determined according to the interest score value in above-mentioned tactful determining module 604
After pin strategy, above-mentioned database update module is used for: according to the update of the output result of the interest score value prediction model
Customer data base.
In the exemplary embodiment, aforementioned schemes, above-mentioned data processing equipment 600 are based on further include: user's portrait is true
Cover half block and target user's recommending module.
Wherein, above-mentioned user's portrait determining module is used for: being determined according to the output result of the interest score value prediction model
The user of the first object user draws a portrait, and user's portrait includes multiple user tags；
Above-mentioned target is used for for recommending module: the forecast demand from second interface is matched according to the user tag,
To determine the second target user from the first object user, second target user is recommended described second and is connect
Mouthful.
Due to each functional module and above-mentioned data processing method of the data processing equipment of the example embodiment of the disclosure
Example embodiment the step of it is corresponding, therefore for those undisclosed details in the apparatus embodiments, please refer in the disclosure
The embodiment for the index stated.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/
Or a step is decomposed into execution of multiple steps etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, mobile terminal or network equipment etc.) is executed according to disclosure embodiment
Data processing method.
Person of ordinary skill in the field it is understood that various aspects of the disclosure can be implemented as system, method or
Program product.Therefore, various aspects of the disclosure can be with specific implementation is as follows, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the disclosure may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this public affairs
The step of opening various illustrative embodiments.
Refering to what is shown in Fig. 7, describing the program product for realizing the above method according to embodiment of the present disclosure
700, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, the program product of the disclosure is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to: electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to: electromagnetism letter
Number, optical signal or above-mentioned any appropriate combination.Readable signal medium can also be other than readable storage medium storing program for executing it is any can
Read medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Program in connection.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to: wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with any combination of one or more programming languages come write for execute the disclosure operation program
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
The electronic equipment 900 of this embodiment according to the disclosure is described referring to Fig. 8.The electronics that Fig. 8 is shown
Equipment 800 is only an example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in figure 8, electronic equipment 800 is showed in the form of universal computing device.The component of electronic equipment 800 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 810, at least one above-mentioned storage unit 820, the different system components of connection
The bus 830 of (including storage unit 820 and processing unit 810).
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 810
Row, so that various according to the disclosure described in the execution of the processing unit 810 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 810 can execute as shown in Figure 1: step S110 is obtained
The forecast demand of customer data base and the first data-interface, wherein the customer data base is according to from the second data-interface
The data information of data information and/or first data-interface determines；Step S120, according to the forecast demand in the use
Matched data in user data library, to obtain the behavioral data of first object user；Step S130 predicts mould based on interest score value
Type determines interest score value of the first object user about target product according to the behavioral data；And step S140, root
The processing strategie to the first object user is determined according to the interest score value.
Storage unit 820 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 8201 and/or cache memory unit 8202, it can further include read-only memory unit (ROM) 8203.
Storage unit 820 can also include program/utility with one group of (at least one) program module 8205
8204, such program module 8205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 830 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 800 can also be with one or more external equipments 1000 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 800 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 800 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 850.Also, electronic equipment 800 can be with
By network adapter 860 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 860 is communicated by bus 830 with other modules of electronic equipment 800.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 800, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In addition, above-mentioned attached drawing is only the schematic theory of the processing according to included by the method for disclosure exemplary embodiment
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
Claims (14)
1. a kind of data processing method characterized by comprising
Obtain the forecast demand of customer data base and the first data-interface, wherein the customer data base is according to from the second number
It is determined according to the data information of interface and/or the data information of first data-interface；
According to the forecast demand in the customer data base matched data, to obtain the behavioral data of first object user；
Based on interest score value prediction model, determine the first object user about the emerging of target product according to the behavioral data
Interesting score value；
The processing strategie to the first object user is determined according to the interest score value.
2. data processing method according to claim 1, which is characterized in that according to the forecast demand in the number of users
According to matched data in library, to obtain the behavioral data of first object user, comprising:
Based on the identity of the first object user, according to the feature of target product in the forecast demand, in the use
Matched data in user data library obtains the behavioral data of the first object user.
3. data processing method according to claim 1, which is characterized in that the method also includes:
It obtains sample data and training machine learning model obtains the interest score value prediction model.
4. data processing method according to claim 3, which is characterized in that obtain sample data and training machine learns mould
Type obtains the interest score value prediction model, comprising:
The corresponding candidate samples data of multidimensional candidate variables are obtained from the customer data base；
For at least one product, the candidate samples data of response data will be generated within a preset time as positive sample data,
And using the candidate samples data of non-output response within a preset time as negative sample data；
For at least one product, screens the multidimensional candidate variables and obtain the corresponding target sample data of target variable；
Based on target sample data training Logic Regression Models, obtain predicting mould about the interest score value of at least one product
Type.
5. data processing method according to claim 4, which is characterized in that screen the multidimensional candidate variables and obtain target
The corresponding target sample data of variable, comprising:
Predictive ability value according to the candidate samples data acquisition per one-dimensional candidate variables；
Using the corresponding candidate variables of predictive ability value for meeting preset condition as the target variable, become with obtaining the target
Measure corresponding target sample data.
6. data processing method according to claim 4 or 5, which is characterized in that the multidimensional candidate variables include: user
Preference data about different product of behavioral data, user internet behavioral data, user about at least one product, user
One or more of social networks data.
7. data processing method according to claim 1, which is characterized in that interest score value prediction model is based on, according to institute
It states behavioral data and determines interest score value of the first object user about target product, comprising:
According to the behavioral data, the corresponding target variable of N kind product is determined, wherein N is the positive integer more than or equal to 1；
The target variable is input to the interest score value prediction model, obtains output result；
According to the output as a result, determining interest score value of the first object user about the N kind product.
8. data processing method according to claim 7, which is characterized in that determined according to the interest score value to described the
The processing strategie of one target user, comprising:
For i-th kind of product in the N kind product:
According to the interest score value about i-th kind of product, by the first object user stratification；
For the first object user of different layers, the different disposal strategy about i-th kind of product is determined, wherein i is greater than etc.
It is less than or equal to N in 1.
9. according to data processing method described in claim 4 or 5 or claim 7 or 8, which is characterized in that the target becomes
Amount include: user about at least one product behavioral data, user internet behavioral data, user about the inclined of different product
One or more of good data, user social contact relation data.
10. data processing method according to claim 9, which is characterized in that determine according to the interest score value to institute
After the processing strategie for stating first object user, the method also includes:
The customer data base is updated according to the output result of the interest score value prediction model.
11. data processing method according to claim 1, which is characterized in that the method also includes:
User's portrait of the first object user, the user are determined according to the output result of the interest score value prediction model
Portrait includes multiple user tags；
The forecast demand from second interface is matched according to the user tag, to determine second from the first object user
Second target user is recommended the second interface by target user.
12. a kind of data processing equipment characterized by comprising
Database obtains module, for obtaining the forecast demand of customer data base and the first data-interface, wherein the number of users
It is determined according to library according to the data information of data information and/or first data-interface from the second data-interface；
Behavioral data obtains module, for according to the forecast demand in the customer data base matched data, to obtain the
The behavioral data of one target user；
Interest score value determining module determines first mesh according to the behavioral data for being based on interest score value prediction model
Mark interest score value of the user about target product；
Tactful determining module, for determining the processing strategie to the first object user according to the interest score value.
13. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that described program is processed
The data processing method as described in any one of claims 1 to 11 is realized when device executes.
14. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs, when one or more of programs are by one or more of processing
When device executes, so that one or more of processors realize the data processing side as described in any one of claims 1 to 11
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910307427.9A CN110070391B (en) | 2019-04-17 | 2019-04-17 | Data processing method and device, computer readable medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910307427.9A CN110070391B (en) | 2019-04-17 | 2019-04-17 | Data processing method and device, computer readable medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110070391A true CN110070391A (en) | 2019-07-30 |
| CN110070391B CN110070391B (en) | 2020-06-19 |
Family
ID=67367926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910307427.9A Active CN110070391B (en) | 2019-04-17 | 2019-04-17 | Data processing method and device, computer readable medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110070391B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110769385A (en) * | 2019-09-26 | 2020-02-07 | 北京淇瑀信息科技有限公司 | Short message sending method and device using strategy optimization model and electronic equipment |
| CN110889490A (en) * | 2019-11-13 | 2020-03-17 | 联想(北京)有限公司 | Prediction method, prediction device, calculation device, and medium |
| CN110956303A (en) * | 2019-10-12 | 2020-04-03 | 未鲲(上海)科技服务有限公司 | Information prediction method, device, terminal and readable storage medium |
| CN111241502A (en) * | 2020-01-14 | 2020-06-05 | 恩亿科(北京)数据科技有限公司 | Cross-device user identification method and device, electronic device and storage medium |
| CN111368131A (en) * | 2020-03-06 | 2020-07-03 | 咪咕音乐有限公司 | User relationship identification method and device, electronic equipment and storage medium |
| CN111460250A (en) * | 2020-03-02 | 2020-07-28 | 平安科技（深圳）有限公司 | Image data cleaning method, image data cleaning device, image data cleaning medium, and electronic apparatus |
| CN111552827A (en) * | 2020-04-28 | 2020-08-18 | 腾讯科技（深圳）有限公司 | Labeling method and device, and behavior willingness prediction model training method and device |
| CN111695084A (en) * | 2020-04-26 | 2020-09-22 | 北京奇艺世纪科技有限公司 | Model generation method, credit score generation method, device, equipment and storage medium |
| CN111861537A (en) * | 2020-05-24 | 2020-10-30 | 上海维信荟智金融科技有限公司 | Operation analysis method and system |
| CN111882420A (en) * | 2020-05-26 | 2020-11-03 | 马上消费金融股份有限公司 | Generation method of response rate, marketing method, model training method and device |
| CN112884449A (en) * | 2021-03-12 | 2021-06-01 | 北京乐学帮网络技术有限公司 | User guiding method, device, computer equipment and storage medium |
| CN112949867A (en) * | 2021-03-29 | 2021-06-11 | 中信银行股份有限公司 | Model value quantification method, device and equipment and readable storage medium |
| CN113256328A (en) * | 2021-05-18 | 2021-08-13 | 深圳索信达数据技术有限公司 | Method, device, computer equipment and storage medium for predicting target client |
| CN113850686A (en) * | 2021-10-08 | 2021-12-28 | 同盾网络科技有限公司 | Insurance application probability determination method and device, storage medium and electronic equipment |
| CN113961774A (en) * | 2021-12-22 | 2022-01-21 | 四川新网银行股份有限公司 | Recommendation method for multi-feature combination strategy |
| CN114971697A (en) * | 2022-05-12 | 2022-08-30 | 建信金融科技有限责任公司 | Data processing method, device, equipment, storage medium and product |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620692A (en) * | 2008-06-30 | 2010-01-06 | 上海全成通信技术有限公司 | Method for analyzing customer churn of mobile communication service |
| CN101694652A (en) * | 2009-09-30 | 2010-04-14 | 西安交通大学 | Network resource personalized recommended method based on ultrafast neural network |
| CN103150696A (en) * | 2011-12-06 | 2013-06-12 | 中兴通讯股份有限公司 | Method and device for selecting potential customer of target value-added service |
| CN103345512A (en) * | 2013-07-06 | 2013-10-09 | 北京品友互动信息技术有限公司 | Online advertising click-through rate forecasting method and device based on user attribute |
| CN103744917A (en) * | 2013-12-27 | 2014-04-23 | 东软集团股份有限公司 | Mixed recommendation method and system |
| CN105224623A (en) * | 2015-09-22 | 2016-01-06 | 北京百度网讯科技有限公司 | The training method of data model and device |
| US20160110761A1 (en) * | 2013-11-01 | 2016-04-21 | Efstratios Ioannidis | Finding the space spanned by user profiles from binary feedback |
| CN107657267A (en) * | 2017-08-11 | 2018-02-02 | 百度在线网络技术（北京）有限公司 | Product potential user method for digging and device |
| CN107730389A (en) * | 2017-09-30 | 2018-02-23 | 平安科技（深圳）有限公司 | Electronic installation, insurance products recommend method and computer-readable recording medium |
| CN108133296A (en) * | 2018-01-17 | 2018-06-08 | 湖南大学 | Forecasting Methodology is attended in a kind of activity of combining environmental data under social networks based on activity |
| CN108898429A (en) * | 2018-06-19 | 2018-11-27 | 平安科技（深圳）有限公司 | Electronic device, preference tendency prediction technique and computer readable storage medium |
| CN108920546A (en) * | 2018-06-13 | 2018-11-30 | 杭州数理大数据技术有限公司 | A kind of stable state label development approach and system based on user demand |
| US20180349514A1 (en) * | 2017-06-05 | 2018-12-06 | International Business Machines Corporation | Domain-oriented predictive model feature recommendation system |
| CN109165983A (en) * | 2018-09-04 | 2019-01-08 | 中国平安人寿保险股份有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
| CN109359998A (en) * | 2018-08-15 | 2019-02-19 | 中国平安人寿保险股份有限公司 | Customer data processing method, device, computer installation and storage medium |
| CN109597940A (en) * | 2018-12-06 | 2019-04-09 | 上海哔哩哔哩科技有限公司 | Based on target group's determination of commercial interest and information-pushing method and system |
-
2019
- 2019-04-17 CN CN201910307427.9A patent/CN110070391B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620692A (en) * | 2008-06-30 | 2010-01-06 | 上海全成通信技术有限公司 | Method for analyzing customer churn of mobile communication service |
| CN101694652A (en) * | 2009-09-30 | 2010-04-14 | 西安交通大学 | Network resource personalized recommended method based on ultrafast neural network |
| CN103150696A (en) * | 2011-12-06 | 2013-06-12 | 中兴通讯股份有限公司 | Method and device for selecting potential customer of target value-added service |
| CN103345512A (en) * | 2013-07-06 | 2013-10-09 | 北京品友互动信息技术有限公司 | Online advertising click-through rate forecasting method and device based on user attribute |
| US20160110761A1 (en) * | 2013-11-01 | 2016-04-21 | Efstratios Ioannidis | Finding the space spanned by user profiles from binary feedback |
| CN103744917A (en) * | 2013-12-27 | 2014-04-23 | 东软集团股份有限公司 | Mixed recommendation method and system |
| CN105224623A (en) * | 2015-09-22 | 2016-01-06 | 北京百度网讯科技有限公司 | The training method of data model and device |
| US20180349514A1 (en) * | 2017-06-05 | 2018-12-06 | International Business Machines Corporation | Domain-oriented predictive model feature recommendation system |
| CN107657267A (en) * | 2017-08-11 | 2018-02-02 | 百度在线网络技术（北京）有限公司 | Product potential user method for digging and device |
| CN107730389A (en) * | 2017-09-30 | 2018-02-23 | 平安科技（深圳）有限公司 | Electronic installation, insurance products recommend method and computer-readable recording medium |
| CN108133296A (en) * | 2018-01-17 | 2018-06-08 | 湖南大学 | Forecasting Methodology is attended in a kind of activity of combining environmental data under social networks based on activity |
| CN108920546A (en) * | 2018-06-13 | 2018-11-30 | 杭州数理大数据技术有限公司 | A kind of stable state label development approach and system based on user demand |
| CN108898429A (en) * | 2018-06-19 | 2018-11-27 | 平安科技（深圳）有限公司 | Electronic device, preference tendency prediction technique and computer readable storage medium |
| CN109359998A (en) * | 2018-08-15 | 2019-02-19 | 中国平安人寿保险股份有限公司 | Customer data processing method, device, computer installation and storage medium |
| CN109165983A (en) * | 2018-09-04 | 2019-01-08 | 中国平安人寿保险股份有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
| CN109597940A (en) * | 2018-12-06 | 2019-04-09 | 上海哔哩哔哩科技有限公司 | Based on target group's determination of commercial interest and information-pushing method and system |
Non-Patent Citations (1)
| Title |
|---|
| 李雅坤: "基于搜索引擎的用户画像构建方法研究", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110769385A (en) * | 2019-09-26 | 2020-02-07 | 北京淇瑀信息科技有限公司 | Short message sending method and device using strategy optimization model and electronic equipment |
| CN110956303A (en) * | 2019-10-12 | 2020-04-03 | 未鲲(上海)科技服务有限公司 | Information prediction method, device, terminal and readable storage medium |
| CN110889490A (en) * | 2019-11-13 | 2020-03-17 | 联想(北京)有限公司 | Prediction method, prediction device, calculation device, and medium |
| CN110889490B (en) * | 2019-11-13 | 2024-04-26 | 联想(北京)有限公司 | Prediction method, prediction device, computing equipment and medium |
| CN111241502A (en) * | 2020-01-14 | 2020-06-05 | 恩亿科(北京)数据科技有限公司 | Cross-device user identification method and device, electronic device and storage medium |
| CN111241502B (en) * | 2020-01-14 | 2023-01-17 | 恩亿科(北京)数据科技有限公司 | Cross-device user identification method and device, electronic device and storage medium |
| WO2021174812A1 (en) * | 2020-03-02 | 2021-09-10 | 平安科技（深圳）有限公司 | Data cleaning method and apparatus for profile, and medium and electronic device |
| CN111460250A (en) * | 2020-03-02 | 2020-07-28 | 平安科技（深圳）有限公司 | Image data cleaning method, image data cleaning device, image data cleaning medium, and electronic apparatus |
| CN111460250B (en) * | 2020-03-02 | 2022-07-08 | 平安科技（深圳）有限公司 | Image data cleaning method, image data cleaning device, image data cleaning medium, and electronic apparatus |
| CN111368131A (en) * | 2020-03-06 | 2020-07-03 | 咪咕音乐有限公司 | User relationship identification method and device, electronic equipment and storage medium |
| CN111368131B (en) * | 2020-03-06 | 2023-08-18 | 咪咕音乐有限公司 | User relationship identification method and device, electronic equipment and storage medium |
| CN111695084A (en) * | 2020-04-26 | 2020-09-22 | 北京奇艺世纪科技有限公司 | Model generation method, credit score generation method, device, equipment and storage medium |
| CN111552827A (en) * | 2020-04-28 | 2020-08-18 | 腾讯科技（深圳）有限公司 | Labeling method and device, and behavior willingness prediction model training method and device |
| CN111861537A (en) * | 2020-05-24 | 2020-10-30 | 上海维信荟智金融科技有限公司 | Operation analysis method and system |
| CN111882420A (en) * | 2020-05-26 | 2020-11-03 | 马上消费金融股份有限公司 | Generation method of response rate, marketing method, model training method and device |
| CN112884449A (en) * | 2021-03-12 | 2021-06-01 | 北京乐学帮网络技术有限公司 | User guiding method, device, computer equipment and storage medium |
| CN112884449B (en) * | 2021-03-12 | 2024-05-14 | 北京乐学帮网络技术有限公司 | User guiding method, device, computer equipment and storage medium |
| CN112949867A (en) * | 2021-03-29 | 2021-06-11 | 中信银行股份有限公司 | Model value quantification method, device and equipment and readable storage medium |
| CN113256328A (en) * | 2021-05-18 | 2021-08-13 | 深圳索信达数据技术有限公司 | Method, device, computer equipment and storage medium for predicting target client |
| CN113256328B (en) * | 2021-05-18 | 2024-02-23 | 深圳索信达数据技术有限公司 | Method, device, computer equipment and storage medium for predicting target clients |
| CN113850686A (en) * | 2021-10-08 | 2021-12-28 | 同盾网络科技有限公司 | Insurance application probability determination method and device, storage medium and electronic equipment |
| CN113850686B (en) * | 2021-10-08 | 2023-11-28 | 同盾网络科技有限公司 | Method and device for determining application probability, storage medium and electronic equipment |
| CN113961774A (en) * | 2021-12-22 | 2022-01-21 | 四川新网银行股份有限公司 | Recommendation method for multi-feature combination strategy |
| CN114971697A (en) * | 2022-05-12 | 2022-08-30 | 建信金融科技有限责任公司 | Data processing method, device, equipment, storage medium and product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110070391B (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070391A (en) | Data processing method, device, computer-readable medium and electronic equipment | |
| Lei et al. | Interactive path reasoning on graph for conversational recommendation | |
| Sin et al. | Bitcoin price prediction using ensembles of neural networks | |
| Vakili et al. | Comprehensive and systematic review of the service composition mechanisms in the cloud environments | |
| Zeng et al. | Intuitionistic fuzzy social network hybrid MCDM model for an assessment of digital reforms of manufacturing industry in China | |
| US20170220928A1 (en) | Method and System for Innovation Management and Optimization under Uncertainty | |
| CN109643247A (en) | The multi-standard adaptive scheduling of mixing cloud infrastructure for market orientation | |
| Fan et al. | Research on multi-objective decision-making under cloud platform based on quality function deployment and uncertain linguistic variables | |
| Becker et al. | ANP-based analysis of ICT usage in Central European enterprises | |
| CN111489095A (en) | Risk user management method and device, computer equipment and storage medium | |
| CN109886699A (en) | Activity recognition method and device, electronic equipment, storage medium | |
| Liang et al. | Towards online deep learning-based energy forecasting | |
| Jajimoggala et al. | Supplier evaluation using hybrid multiple criteria decision making approach | |
| Noori | Developing a CBR system for marketing mix planning and weighting method selection using fuzzy AHP | |
| CN113672797A (en) | Content recommendation method and device | |
| AU2015203754A1 (en) | System and method for prescriptive analytics | |
| CN114387024A (en) | User analysis system for E-commerce repurchase behavior based on Mamdani algorithm | |
| Guo et al. | A multi-stage group decision making for strategic supplier selection based on prospect theory with interval-valued q-rung orthopair fuzzy linguistic sets | |
| Xu et al. | Optimizing long-term value for auction-based recommender systems via on-policy reinforcement learning | |
| WO2021077977A1 (en) | Method for analyzing transaction data in wind power bidding market, device, apparatus, and medium | |
| Keles et al. | IBMMS decision support tool for management of bank telemarketing campaigns | |
| CN110837962A (en) | Power customer viscosity calculation method | |
| CN109615162A (en) | User grouping processing method and processing device, electronic equipment and storage medium | |
| Riedel et al. | Evolving multilevel forecast combination models-an experimental study | |
| CN117473457B (en) | Big data mining method and system based on digital service |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210910 Address after: Room 209, building 18, No. 998, Wenyi West Road, Wuchang Street, Yuhang District, Hangzhou City, Zhejiang Province, 310012 Patentee after: TONGDUN TECHNOLOGY Co.,Ltd. Address before: Room 704, building 18, No. 998, Wenyi West Road, Wuchang Street, Yuhang District, Hangzhou City, Zhejiang Province Patentee before: TONGDUN HOLDINGS Co.,Ltd. |